Pith. sign in

← back to paper

Review history

arxiv: 2605.15250 · 3 revisions

GQLA: Group-Query Latent Attention for Hardware-Adaptive Large Language Model Decoding

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
    131285 ms 211 in 11986 out 2026-08-02T13:58:08.160389+00:00
  2. 2026-06-30 UNVERDICTED LOW v0.9.1-grok novelty 7.0
    34944 ms 5818 in 1246 out 2026-06-30T21:33:56.373336+00:00
  3. 2026-05-19 UNVERDICTED LOW v0.9.0 novelty 6.0
    35325 ms 5818 in 1393 out 2026-05-19T17:17:06.763524+00:00